od FAL AI (Kling)
Kling O3 Standard Ref2V (FAL)
Kling O3 Standard — reference-to-video with @Element character locking + @Image style refs (3-15s, 720p)
fal-kling-o3-std-ref2vGenerate video with this model.
/api/v1/videos/generationsGET /api/v1/videos/generations{
"model": "fal-kling-o3-std-ref2v",
"prompt": "A cinematic drone shot over a coastal city at sunset",
"duration": 5,
"resolution": "720p",
"image_url": "https://example.com/start-frame.jpg"
}curl -X POST https://kunya.ai/api/v1/videos/generations \
-H "Authorization: Bearer kunya_YOUR_API_KEY" \
-H "Content-Type: application/json"
-d '{"model":"fal-kling-o3-std-ref2v","prompt":"A cinematic drone shot over a coastal city at sunset","duration":5,"resolution":"720p","image_url":"https://example.com/start-frame.jpg"}'FAL AI (Luma)
Fast version of Ray 2 for quicker generation (5s or 9s)
Dokumentacja APIFAL AI (Google Veo)
Veo 3.1 via FAL — can disable native audio ($0.20/s silent, $0.40/s with audio @ 1080p)
Dokumentacja APIKunya (Kling)
Kling O3 (V3 Omni) — best-in-class image-to-video with reference images, elements, and multi-shot (3-15s)
Dokumentacja APIGoogle Gemini Omni 1.1 Flash direct — append a 3–10s continuation to a clip (multi-turn chains to ~40s)
Dokumentacja API